Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2008 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3452. Min Range: -3.3452
Max Act: 3.3452. Min Act: -0.1700
Data Index: 2971816 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3452. Min Range: -3.3452
Max Act: 3.3452. Min Act: -0.1700
Data Index: 1475870 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3452. Min Range: -3.3452
Max Act: 3.3452. Min Act: -0.1700
Data Index: 2453628 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3452. Min Range: -3.3452
Max Act: 3.3452. Min Act: -0.1700
Data Index: 3154676 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3452. Min Range: -3.3452
Max Act: 3.2981. Min Act: -0.1700
Data Index: 6941389 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3452. Min Range: -3.3452
Max Act: 3.3138. Min Act: -0.1700
Data Index: 5154952 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3452. Min Range: -3.3452
Max Act: 3.2981. Min Act: -0.1700
Data Index: 5704682 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3452. Min Range: -3.3452
Max Act: 3.2824. Min Act: -0.1700
Data Index: 3972975 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3452. Min Range: -3.3452
Max Act: 3.2667. Min Act: -0.1700
Data Index: 6963516 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3452. Min Range: -3.3452
Max Act: 3.3138. Min Act: -0.1700
Data Index: 950490 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3452. Min Range: -3.3452
Max Act: 3.2824. Min Act: -0.1700
Data Index: 6812803 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3452. Min Range: -3.3452
Max Act: 3.2353. Min Act: -0.1700
Data Index: 49124 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3452. Min Range: -3.3452
Max Act: 3.2353. Min Act: -0.1700
Data Index: 1183586 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3452. Min Range: -3.3452
Max Act: 3.2196. Min Act: -0.1700
Data Index: 2122995 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3452. Min Range: -3.3452
Max Act: 3.2196. Min Act: -0.1700
Data Index: 2398547 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3452. Min Range: -3.3452
Max Act: 3.2196. Min Act: -0.1700
Data Index: 555231 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3452. Min Range: -3.3452
Max Act: 3.2039. Min Act: -0.1700
Data Index: 1573149 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3452. Min Range: -3.3452
Max Act: 3.2039. Min Act: -0.1700
Data Index: 648259 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3452. Min Range: -3.3452
Max Act: 3.2039. Min Act: -0.1700
Data Index: 6555925 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3452. Min Range: -3.3452
Max Act: 3.2039. Min Act: -0.1700
Data Index: 712973 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19